←back to thread

DeepSeek-v3.1

(api-docs.deepseek.com)
776 points wertyk | 4 comments | 21 Aug 25 19:06 UTC | HN request time: 0s | source
Show context
rsanek ◴[22 Aug 25 03:30 UTC] No.44980753[source]▶
Looks to be the ~same intelligence as gpt-oss-120B, but about 10x slower and 3x more expensive?

https://artificialanalysis.ai/models/deepseek-v3-1-reasoning

replies(5): >>44981187 #>>44981737 #>>44981789 #>>44982171 #>>44982769 #
okasaki ◴[22 Aug 25 07:05 UTC] No.44981737[source]▶
My experience is that gpt-oss doesn't know much about obscure topics, so if you're using it for anything except puzzles or coding in popular languages, it won't do well as the bigger models.

It's knowledge seems to be lacking even compared to gpt3.

No idea how you'd benchmark this though.

replies(2): >>44981768 #>>44984205 #
1. easygenes ◴[22 Aug 25 07:13 UTC] No.44981768[source]▶
Something I was doing informally that seems very effective is asking for details about smaller cities and towns and lesser points of interest around the world. Bigger models tend to have a much better understanding and knowledge base for the more obscure places.
replies(1): >>44983215 #
2. scotty79 ◴[22 Aug 25 11:31 UTC] No.44983215[source]▶
I would really love if they figured out how to train a model that doesn't have any such knowledge baked it, but knows where to look for it. Maybe even has a clever database for that. Knowing this kind of trivia like this consistently of the top of your head is a sign of deranged mind, artificial or not.
replies(2): >>44983518 #>>44985867 #
3. okasaki ◴[22 Aug 25 12:07 UTC] No.44983518[source]▶
Would that work as well? If I ask a big model to write like Shakespeare it just knows intuitively how to do that. If it didn't and had to look up how to do that, I'm not sure it would do a good job.
4. bigmadshoe ◴[22 Aug 25 15:34 UTC] No.44985867[source]▶
The problem is that these models can't reason about what they do and do not know, so right now you basically need to tune it to: 1) always look up all trivia, or 2) occasionally look up trivia when it "seems complex" enough.